Vendor: Cyan Eclipse Technologies · Platforms: MCP over stdio (HTTP transport on roadmap)
Certification scope
CERTIFIED(local) — Eclipse Bazaar Test Bench 2026-10-25, 13/14 checks pass, 1 na (U1 auth: stdio process boundary). Run by W-003 (Verity), suites/dispatch.py.
What it does
- One canonical, versioned, hash-bound draft: any post-approval edit invalidates the approval by name
- Syndication as per-platform drafts via sanctioned-API-shaped adapters (beehiiv, Ghost)
- Read-only platforms (Substack) get a paste pack, never a write; the beehiiv adapter has no publish method
- Unified analytics with per-source metric definitions: differing definitions flagged DEFINITIONS_DIFFER, never blended
- Hash-chained receipts over drafts, approvals, syndications and analytics runs
Tools
draft_createdraft_previewdraft_approvesyndicate_draftsanalytics_reportreceipt_list
Problems it addresses
- I write once and re-post the same newsletter to every platform by hand
- Platforms define the same metric differently and my reports blend them silently
- Edits made after approval should void the approval automatically
Not tested
- Live platform wiring: adapters run against fixtures and local stub HTTP servers shaped like the real APIs. beehiiv signup is an owner Wave-2 item; no Ghost instance runs here; Substack live reads (official MCP analytics) not exercised.
Bench scorecard: test-bench/results/eclipse-dispatch-mcp-2026-10-25.json
Evaluation-intake listing
This listing records the tool's place in the Bazaar's evaluation
and monitoring pipeline, with the evidence gathered so far printed above — verdict, scope,
and not-tested items included. It is not sold on this site, and its presence in the catalog
is not a claim beyond that evidence. The service behind every verdict is the bench:
what a bench run buys →